# FPConv: Learning Local Flattening for Point Convolution

arXiv: https://arxiv.org/abs/2002.10701 · HTML: https://mlsanity.com/paper/2002.10701/

## Key facts

- Cited by 55 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Feb 2020.

## Built on by (most cited first, 30 of 55)

- [PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds](https://mlsanity.com/paper/2103.14635/) (2021)
- [Bidirectional Projection Network for Cross Dimension Scene Understanding](https://mlsanity.com/paper/2103.14326/) (2021)
- [One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation](https://mlsanity.com/paper/2104.02246/) (2021)
- [Surface Representation for Point Clouds](https://mlsanity.com/paper/2205.05740/) (2022)
- [PointMixer: MLP-Mixer for Point Cloud Understanding](https://mlsanity.com/paper/2111.11187/) (2021)
- [Pri3D: Can 3D Priors Help 2D Representation Learning?](https://mlsanity.com/paper/2104.11225/) (2021)
- [PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysis](https://mlsanity.com/paper/2112.04903/) (2021)
- [Contrastive Boundary Learning for Point Cloud Segmentation](https://mlsanity.com/paper/2203.05272/) (2022)
- [SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Instance Segmentation](https://mlsanity.com/paper/2311.17707/) (2023)
- [OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation](https://mlsanity.com/paper/2403.14418/) (2024)
- [Attention-based Point Cloud Edge Sampling](https://mlsanity.com/paper/2302.14673/) (2023)
- [Transformers in 3D Point Clouds: A Survey](https://mlsanity.com/paper/2205.07417/) (2022)
- [Learning Inner-Group Relations on Point Clouds](https://mlsanity.com/paper/2108.12468/) (2021)
- [Dual Transformer for Point Cloud Analysis](https://mlsanity.com/paper/2104.13044/) (2021)
- [Efficient 3D Deep LiDAR Odometry](https://mlsanity.com/paper/2111.02135/) (2021)
- [Omni-supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning](https://mlsanity.com/paper/2105.10203/) (2021)
- [Not All Voxels Are Equal: Semantic Scene Completion from the Point-Voxel Perspective](https://mlsanity.com/paper/2112.12925/) (2021)
- [Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysis](https://mlsanity.com/paper/2212.08892/) (2022)
- [DSPoint: Dual-scale Point Cloud Recognition with High-frequency Fusion](https://mlsanity.com/paper/2111.10332/) (2021)
- [Point Cloud Learning with Transformer](https://mlsanity.com/paper/2104.13636/) (2021)
- [MM-3DScene: 3D Scene Understanding by Customizing Masked Modeling with Informative-Preserved Reconstruction and Self-Distilled Consistency](https://mlsanity.com/paper/2212.09948/) (2022)
- [TO-Scene: A Large-scale Dataset for Understanding 3D Tabletop Scenes](https://mlsanity.com/paper/2203.09440/) (2022)
- [DLA-Net: Learning Dual Local Attention Features for Semantic Segmentation of Large-Scale Building Facade Point Clouds](https://mlsanity.com/paper/2106.00376/) (2021)
- [Continuous Conditional Random Field Convolution for Point Cloud Segmentation](https://mlsanity.com/paper/2110.06085/) (2021)
- [PointMatch: A Consistency Training Framework for Weakly Supervised Semantic Segmentation of 3D Point Clouds](https://mlsanity.com/paper/2202.10705/) (2022)
- [Self-Supervised Image Representation Learning with Geometric Set Consistency](https://mlsanity.com/paper/2203.15361/) (2022)
- [Investigate Indistinguishable Points in Semantic Segmentation of 3D Point Cloud](https://mlsanity.com/paper/2103.10339/) (2021)
- [Task-Aware Sampling Layer for Point-Wise Analysis](https://mlsanity.com/paper/2107.04291/) (2021)
- [MKConv: Multidimensional Feature Representation for Point Cloud Analysis](https://mlsanity.com/paper/2107.12655/) (2021)
- [Retro-FPN: Retrospective Feature Pyramid Network for Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2308.09314/) (2023)

## Abstract (arXiv)

We introduce FPConv, a novel surface-style convolution operator designed for 3D point cloud analysis. Unlike previous methods, FPConv doesn't require transforming to intermediate representation like 3D grid or graph and directly works on surface geometry of point cloud. To be more specific, for each point, FPConv performs a local flattening by automatically learning a weight map to softly project surrounding points onto a 2D grid. Regular 2D convolution can thus be applied for efficient feature learning. FPConv can be easily integrated into various network architectures for tasks like 3D object classification and 3D scene segmentation, and achieve comparable performance with existing volumetric-type convolutions. More importantly, our experiments also show that FPConv can be a complementary of volumetric convolutions and jointly training them can further boost overall performance into state-of-the-art results.